Computational Biologist / Data Scientist (Scientist or Senior Scientist)

The opportunity

Codebreaker is building a functional genomics platform to connect human genetic variation to cellular function at scale. Unlike standard CRISPR-knockout Perturb-seq workflows, Codebreaker installs specific human variants via pooled HDR in primary human cells and reads them out with scRNA-seq, giving variant-level rather than gene-level resolution. These datasets directly train Codebreaker's proprietary variant-effect scoring model, so the person in this role has unusually direct leverage over what the company can learn and predict.

This is a hands-on scientific role. You will analyze large-scale pooled-variant Perturb-seq and single-cell functional genomics experiments, from primary data through perturbation-effect estimation, differential expression, biological interpretation, and the generation of datasets for predictive modeling. At the senior level, you will lead this work. You will build scalable analysis pipelines while working directly with new datasets to understand the biology, diagnose problems and generate hypotheses.

You will also help shape the experiments we run. This requires a strong understanding of transcription and gene regulation, the capabilities and limitations of single-cell RNA sequencing, and the statistical judgment to design experiments that can answer meaningful biological questions. You will work closely with experimental biologists to design variant installation experiments and disease- and cell-type-specific assays, and with computational and ML colleagues to use these data to understand and predict the consequences of genetic perturbations and human variation.

What you will do

• Analyze Codebreaker's variant Perturb-seq and related single-cell functional genomics experiments, from primary data through perturbation-effect estimation, differential expression and biological interpretation.
• Build robust, scalable pipelines for QC, guide assignment, differential expression, perturbation-effect estimation, visualization, and generation of model-ready datasets.
• Apply statistical approaches for perturbational single-cell data that account for experimental design, biological replication, perturbation efficiency, donor and batch effects, and cell-state heterogeneity.
• Work directly with new datasets to separate biological signal from technical artifacts, find unexpected biology and generate hypotheses.
• Work with ML colleagues to build training and evaluation datasets and to test model predictions experimentally.
• Integrate single-cell data with human genetics, regulatory annotations and sequence-based predictions to interpret perturbation effects.
• Write reproducible, tested analysis code that holds up as experimental scale grows.

At the Senior Scientist level, you will also

• Own the computational strategy for Codebreaker's perturbation experiments and decide which analyses and experiments come next.
• Lead the design of Perturb-seq experiments and disease- and cell-type-specific assays with experimental scientists, including perturbations, controls, replication, cellular context, sequencing depth and QC criteria.
• Develop new statistical methods where existing ones fall short.
• Set the scientific practices and infrastructure the computational team works within, and mentor junior scientists.

What we are looking for

• PhD in computational biology, genomics, bioinformatics, systems biology, statistical genetics, biostatistics or a related quantitative field.
• Hands-on experience analyzing single-cell RNA-seq data, and a working understanding of its biology, statistics and technical limitations.
• A solid understanding of transcription and gene regulation, and the ability to reason about how genetic perturbations produce molecular and cellular phenotypes.
• Sound statistical judgment in differential expression, replication and high-dimensional data.
• Strong programming skills in Python and/or R, with experience writing analysis code that others can run and trust.
• Enough familiarity with predictive models in regulatory genomics to evaluate them and understand their limitations.
• Clear communication and comfort working directly with experimental scientists.

For the Senior Scientist level

• 5+ years of post-PhD research and/or industry experience, or a PhD with substantial prior industry experience in a delivery-focused environment.
• Deep expertise in Perturb-seq, CRISPR screens or related functional genomics experiments.
• A track record of designing experiments, not only analyzing them.
• Evidence of shipping into a team: either post-PhD industry experience or a concrete, adopted deliverable from an academic lab (a tool used outside your lab, a released dataset, a method adopted by collaborators).

Especially valuable

• Direct experience designing and analyzing large-scale Perturb-seq experiments.
• Experience with human genetics and variant-effect studies, including regulatory variants, eQTLs, fine-mapping, saturation mutagenesis, MPRA or related approaches.
• Experience applying regulatory genomics, sequence-to-function or perturbation-response models to biological questions.
• Experience with multimodal single-cell data, primary human cells, iPSC-derived systems, immune cells or other complex human cell models.
• A first-author publication in a relevant area (single-cell, regulatory genomics, statistical genetics), or a released tool or method that has been adopted outside its original lab.
• Prior clinical genomics or diagnostics industry experience.

Why Codebreaker

This role offers unusual scientific and technical ownership. You will help define how Codebreaker designs and analyzes single-cell perturbation experiments, how we represent perturbation effects, and how experimental data and predictive models inform the next experiments.

The right person will have room to build systems, invent analyses, influence experimental strategy and pursue difficult biological questions. If you are happiest moving between biology, statistics and software, and want that work to directly shape the experiments we run, we would like to meet you.

Compensation and benefits

Compensation: Scientist $120,000–$150,000 per year; Senior Scientist $150,000–$190,000 per year. Compensation also includes meaningful early-stage equity. Where an offer lands within the range depends on demonstrated scope, depth and prior impact.

Benefits: Competitive benefits package. Full details are shared during the interview process.